INDEX

Explanations

instances of the preposition 'in' followed by a noun phrase

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tein

-0.79

IAS

-0.68

uploads

-0.63

onomy

-0.62

ilus

-0.61

ISS

-0.61

âĢ¢âĢ¢

-0.59

Discuss

-0.58

DOM

-0.58

friend

-0.57

POSITIVE LOGITS

 handy

1.35

escap

0.80

uit

0.76

 contact

0.75

offensive

0.71

 shape

0.70

 cans

0.69

ear

0.69

ulhu

0.68

umber

0.68

Activations Density 0.085%

instances of the preposition 'in' followed by a noun phrase

No Comments

No Known Activations